{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T18:18:00Z","timestamp":1780078680278,"version":"3.54.0"},"reference-count":75,"publisher":"MIT Press","issue":"9","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,8,19]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Electromagnetic source imaging (ESI) and independent component analysis (ICA) are two popular and apparently dissimilar frameworks for M\/EEG analysis. This letter shows that the two frameworks can be linked by choosing biologically inspired source sparsity priors. We demonstrate that ESI carried out by the sparse Bayesian learning (SBL) algorithm yields source configurations composed of a few active regions that are also maximally independent from one another. In addition, we extend the standard SBL approach to source imaging in two important directions. First, we augment the generative model of M\/EEG to include artifactual sources. Second, we modify SBL to allow for efficient model inversion with sequential data. We refer to this new algorithm as recursive SBL (RSBL), a source estimation filter with potential for online and offline imaging applications. We use simulated data to verify that RSBL can accurately estimate and demix cortical and artifactual sources under different noise conditions. Finally, we show that on real error-related EEG data, RSBL can yield single-trial source estimates in agreement with the experimental literature. Overall, by demonstrating that ESI can produce maximally independent sources while simultaneously localizing them in cortical space, we bridge the gap between the ESI and ICA frameworks for M\/EEG analysis.<\/jats:p>","DOI":"10.1162\/neco_a_01415","type":"journal-article","created":{"date-parts":[[2021,6,30]],"date-time":"2021-06-30T21:34:25Z","timestamp":1625088865000},"page":"2408-2438","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":31,"title":["Bridging M\/EEG Source Imaging and Independent Component Analysis Frameworks Using Biologically Inspired Sparsity Priors"],"prefix":"10.1162","volume":"33","author":[{"given":"Alejandro","family":"Ojeda","sequence":"first","affiliation":[{"name":"Neural Engineering and Translation Labs, Department of Psychiatry, and Department of Electrical and Computer Engineering, University of California San Diego, La Jolla, CA 92093 U.S.A. alejo.ojeda83@gmail dot com"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kenneth","family":"Kreutz-Delgado","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of California San Diego, La Jolla, CA 92093 U.S.A. kreutz@eng.ucsd.edu"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jyoti","family":"Mishra","sequence":"additional","affiliation":[{"name":"Neural Engineering and Translation Labs, Department of Psychiatry, University of California San Diego, CA 92093, U.S.A. jymishra@health.ucsd.edu"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","published-online":{"date-parts":[[2021,8,19]]},"reference":[{"issue":"4","key":"2021121723253931000_B1","doi-asserted-by":"crossref","first-page":"655","DOI":"10.1007\/s10548-019-00705-z","article-title":"Quantifying the effect of demixing approaches on directed connectivity estimated between reconstructed EEG sources","volume":"32","author":"Anzolin","year":"2019","journal-title":"Brain Topography"},{"key":"2021121723253931000_B2","doi-asserted-by":"crossref","DOI":"10.1016\/j.jneumeth.2020.108740","article-title":"A systematic review of EEG source localization techniques and their applications on diagnosis of brain abnormalities","volume":"339","author":"Asadzadeh","year":"2020","journal-title":"Journal of Neuroscience Methods"},{"key":"2021121723253931000_B3","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511804779","author":"Barber","year":"2012","journal-title":"Bayesian reasoning and machine learning"},{"issue":"6","key":"2021121723253931000_B4","doi-asserted-by":"crossref","first-page":"1129","DOI":"10.1162\/neco.1995.7.6.1129","article-title":"An information-maximization approach to blind separation and blind deconvolution","volume":"7","author":"Bell","year":"1995","journal-title":"Neural Computation"},{"issue":"4","key":"2021121723253931000_B5","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1093\/biomet\/asr054","article-title":"Sparse estimation of a covariance matrix","volume":"98","author":"Bien","year":"2011","journal-title":"Biometrika"},{"key":"2021121723253931000_B6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fninf.2015.00016","article-title":"The PREP pipeline: Standardized preprocessing for large-scale EEG analysis","volume":"9","author":"Bigdely-Shamlo","year":"2015","journal-title":"Frontiers in Neuroinformatics"},{"key":"2021121723253931000_B7","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1016\/j.neuroimage.2013.01.040","article-title":"Measure projection analysis: A probabilistic approach to EEG source comparison and multisubject inference","volume":"72","author":"Bigdely-Shamlo","year":"2013","journal-title":"NeuroImage"},{"issue":"May","key":"2021121723253931000_B8","article-title":"Unmixing EEG Inverse solutions based on brain segmentation.","volume":"12","author":"Biscay","year":"2018","journal-title":"Frontiers in Neuroscience"},{"key":"2021121723253931000_B9","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1016\/j.jmbbm.2011.04.017","article-title":"A coupled electromechanical model for the excitation-dependent contraction of skeletal muscle","volume":"4","author":"B\u00f6l","year":"2011","journal-title":"Journal of the Mechanical Behavior of Biomedical Material"},{"issue":"1","key":"2021121723253931000_B10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/2326263X.2015.1008956","article-title":"BNCI Horizon 2020: Towards a roadmap for the BCI community","volume":"2","author":"Brunner","year":"2015","journal-title":"Brain-Computer Interfaces"},{"key":"2021121723253931000_B11","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.neuroimage.2017.05.045","article-title":"Development of the error-monitoring system from ages 9\u201335: Unique insight provided by MRI-constrained source localization of EEG","volume":"157","author":"Buzzell","year":"2017","journal-title":"NeuroImage"},{"key":"2021121723253931000_B12","doi-asserted-by":"crossref","DOI":"10.1109\/CISS.2011.5766179","article-title":"Sparsity penalties in dynamical system estimation.","author":"Charles","year":"2011","journal-title":"Proceedings of the 2011 45th Annual Conference on Information Sciences and Systems"},{"issue":"4","key":"2021121723253931000_B13","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1109\/TNSRE.2010.2053387","article-title":"Learning from EEG error-related potentials in noninvasive brain-computer interfaces","volume":"18","author":"Chavarriaga","year":"2010","journal-title":"IEEE Transactions on Neural Systems and Rehabilitation Engineering"},{"key":"2021121723253931000_B14","doi-asserted-by":"crossref","first-page":"2122","DOI":"10.1109\/TBME.2010.2050319","article-title":"Estimation of cortical connectivity from EEG using state-space models","volume":"57","author":"Cheung","year":"2010","journal-title":"IEEE Transactions on Biomedical Engineering"},{"key":"2021121723253931000_B15","doi-asserted-by":"crossref","DOI":"10.1002\/0470845899","author":"Cichocki","year":"2002","journal-title":"Adaptive blind signal and image processing"},{"issue":"3","key":"2021121723253931000_B16","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1016\/0165-1684(94)90029-9","article-title":"Independent component analysis: A new concept?","volume":"36","author":"Comon","year":"1994","journal-title":"Signal Processing"},{"issue":"7","key":"2021121723253931000_B17","doi-asserted-by":"crossref","first-page":"2477","DOI":"10.1109\/TSP.2005.849172","article-title":"Sparse solutions to linear in verse problems with multiple measurement vectors","volume":"53","author":"Cotter","year":"2005","journal-title":"IEEE Transactions on Signal Processing"},{"issue":"2","key":"2021121723253931000_B18","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1162\/jocn.1993.5.2.162","article-title":"Improved localization of cortical activity by combining EEG and MEG with MRI cortical surface reconstruction: A linear approach","volume":"5","author":"Dale","year":"1993","journal-title":"Journal of Cognitive Neuroscience"},{"issue":"2","key":"2021121723253931000_B19","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1002\/hbm.20171","article-title":"Generic head models for atlas-based EEG source analysis","volume":"27","author":"Darvas","year":"2006","journal-title":"Human Brain Mapping"},{"issue":"2","key":"2021121723253931000_B20","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1016\/j.neuroimage.2009.04.062","article-title":"Dynamic causal modelling of distributed electromagnetic responses","volume":"47","author":"Daunizeau","year":"2009","journal-title":"NeuroImage"},{"issue":"2","key":"2021121723253931000_B21","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0030135","article-title":"Independent EEG sources are dipolar","volume":"7","author":"Delorme","year":"2012","journal-title":"PLOS One"},{"issue":"3","key":"2021121723253931000_B22","doi-asserted-by":"crossref","first-page":"968","DOI":"10.1016\/j.neuroimage.2006.01.021","article-title":"An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest","volume":"31","author":"Desikan","year":"2006","journal-title":"NeuroImage"},{"issue":"15","key":"2021121723253931000_B23","doi-asserted-by":"crossref","first-page":"4357","DOI":"10.1002\/hbm.24707","article-title":"Data-driven model optimization for optically pumped magnetometer sensor arrays","volume":"40","author":"Duque-Mu\u00f1oz","year":"2019","journal-title":"Human Brain Mapping"},{"key":"2021121723253931000_B24","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1016\/j.neuroimage.2014.12.040","article-title":"Automated model selection in covariance estimation and spatial whitening of MEG and EEG signals","volume":"108","author":"Engemann","year":"2015","journal-title":"NeuroImage"},{"key":"2021121723253931000_B25","first-page":"383","volume-title":"Advances in neural information processing systems","author":"Faul","year":"2002"},{"issue":"3","key":"2021121723253931000_B26","doi-asserted-by":"crossref","first-page":"1104","DOI":"10.1016\/j.neuroimage.2007.09.048","article-title":"Multiple sparse priors for the M\/EEG inverse problem","volume":"39","author":"Friston","year":"2008","journal-title":"NeuroImage"},{"issue":"2","key":"2021121723253931000_B27","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1016\/j.neuroimage.2008.12.012","article-title":"A hierarchical Bayesian method to resolve an inverse problem of MEG contaminated with eye movement artifacts","volume":"45","author":"Fujiwara","year":"2009","journal-title":"NeuroImage"},{"issue":"6","key":"2021121723253931000_B28","doi-asserted-by":"crossref","first-page":"1561","DOI":"10.1109\/TBME.2012.2189713","article-title":"A state-space modeling approach for localization of focal current sources from MEG","volume":"59","author":"Fukushima","year":"2012","journal-title":"IEEE Transactions on Biomedical Engineering"},{"key":"2021121723253931000_B29","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1016\/j.neuroimage.2014.09.066","article-title":"MEG source reconstruction based on identification of directed source interactions on whole-brain anatomical networks.","volume":"105","author":"Fukushima","year":"2015","journal-title":"NeuroImage"},{"issue":"2","key":"2021121723253931000_B30","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1016\/j.neuroimage.2004.02.022","article-title":"A solution to the dynamical inverse problem of EEG generation using spatiotemporal Kalman filtering","volume":"23","author":"Galka","year":"2004","journal-title":"NeuroImage"},{"key":"2021121723253931000_B31","author":"Gehring","year":"2011","journal-title":"The error-related negativity (ERN\/Ne)"},{"key":"2021121723253931000_B32","first-page":"2914","article-title":"Estimation of dynamic neural activity using a Kalman filter approach based on physiological models","author":"Giraldo","year":"2010","journal-title":"Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society"},{"key":"2021121723253931000_B33","doi-asserted-by":"crossref","DOI":"10.1186\/1475-925X-9-45","article-title":"OpenMEEG: Open-source software for quasistatic bioelectromagnetics","volume":"9","author":"Gramfort","year":"2010","journal-title":"Biomedical Engineering Online"},{"issue":"1","key":"2021121723253931000_B34","doi-asserted-by":"crossref","DOI":"10.1186\/1743-0003-4-46","article-title":"Review on solving the forward problem in EEG source analysis","volume":"4","author":"Hallez","year":"2007","journal-title":"Journal of NeuroEngineering and Rehabilitation"},{"key":"2021121723253931000_B35","doi-asserted-by":"crossref","DOI":"10.3389\/fnhum.2011.00076","article-title":"A parametric empirical Bayesian framework for the EEG\/MEG inverse problem: Generative models for multi-subject and multi-modal integration.","volume":"5","author":"Henson","year":"2011","journal-title":"Frontiers in Human Neuroscience"},{"key":"2021121723253931000_B36","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.neuroimage.2015.12.019","article-title":"The New York Head\u2014A precise standardized volume conductor model for EEG source localization and tES targeting","volume":"140","author":"Huang","year":"2016","journal-title":"NeuroImage"},{"key":"2021121723253931000_B37","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.jneumeth.2017.06.011","article-title":"Evaluation of a minimum-norm based beamforming technique, sLORETA, for reducing tonic muscle contamination of EEG at sensor level","volume":"288","author":"Janani","year":"2017","journal-title":"Journal of Neuroscience Methods"},{"issue":"3","key":"2021121723253931000_B38","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1109\/JPROC.2003.823141","article-title":"Unscented filtering and nonlinear estimation","volume":"92","author":"Julier","year":"2004","journal-title":"Proceedings of the IEEE"},{"key":"2021121723253931000_B39","doi-asserted-by":"crossref","DOI":"10.1111\/1469-8986.3720163","article-title":"Removing electroencephalographic artifacts by blind source separation.","author":"Jung","year":"2000","journal-title":"Psychophysiology"},{"issue":"1","key":"2021121723253931000_B40","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1115\/1.3662552","article-title":"A new approach to linear filtering and prediction problems","volume":"81","author":"Kalman","year":"1960","journal-title":"Journal of Basic Engineering"},{"key":"2021121723253931000_B41","article-title":"Sparsity-based Kalman filters for data assimilation.","author":"Kang","year":"2018"},{"key":"2021121723253931000_B42","doi-asserted-by":"crossref","first-page":"894","DOI":"10.1016\/j.neuroimage.2011.11.020","article-title":"A spatiotemporal dynamic distributed solution to the MEG inverse problem","volume":"63","author":"Lamus","year":"2012","journal-title":"NeuroImage"},{"key":"2021121723253931000_B43","first-page":"1017","volume-title":"Advances in neural information processing systems","author":"Le","year":"2011"},{"issue":"August","key":"2021121723253931000_B44","article-title":"Incorporating priors for EEG source imaging and connectivity analysis","volume":"9","author":"Lei","year":"2015","journal-title":"Frontiers in Neuroscience"},{"key":"2021121723253931000_B45","first-page":"556","volume-title":"Advances in neural information processing systems","author":"Lewicki","year":"1998"},{"issue":"3","key":"2021121723253931000_B46","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1162\/neco.1992.4.3.415","article-title":"Bayesian interpolation","volume":"4","author":"MacKay","year":"1992","journal-title":"Neural Computation"},{"key":"2021121723253931000_B47","author":"MacKay","year":"2008","journal-title":"Information theory, inference, and learning algorithms"},{"key":"2021121723253931000_B48","doi-asserted-by":"crossref","first-page":"10979","DOI":"10.1073\/pnas.94.20.10979","article-title":"Blind separation of auditory event-related brain responses into independent components","volume":"94","author":"Makeig","year":"1997","journal-title":"Proceedings of the National Academy of Sciences of the United States of America"},{"key":"2021121723253931000_B49","author":"Makeig","year":"2011","journal-title":"ERP features and EEG dynamics"},{"key":"2021121723253931000_B50","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-0745-0","author":"Neal","year":"1996","journal-title":"Lecture notes in statistics: Vol. 118, Bayesian learning for neural network."},{"key":"2021121723253931000_B51","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.jneumeth.2009.07.006","article-title":"Minimum overlap component analysis (MOCA) of EEG\/MEG data for more than two sources","volume":"183","author":"Nolte","year":"2009","journal-title":"Journal of Neuroscience Methods"},{"key":"2021121723253931000_B52","doi-asserted-by":"crossref","DOI":"10.1093\/acprof:oso\/9780195050387.001.0001","author":"Nunez","year":"2006","journal-title":"Electric fields of the brain"},{"issue":"8","key":"2021121723253931000_B53","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1016\/j.neuroimage.2018.03.048","article-title":"Fast and robust block-sparse Bayesian learning for EEG source imaging","volume":"174","author":"Ojeda","year":"2018","journal-title":"NeuroImage"},{"key":"2021121723253931000_B54","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1016\/j.neuroimage.2013.04.046","article-title":"A switching multi-scale dynamical network model of EEG\/MEG","volume":"83","author":"Olier","year":"2013","journal-title":"NeuroImage"},{"issue":"6","key":"2021121723253931000_B55","doi-asserted-by":"crossref","first-page":"808","DOI":"10.1016\/j.neubiorev.2006.06.007","article-title":"Imaging human EEG dynamics using independent component analysis","volume":"30","author":"Onton","year":"2006","journal-title":"Neuroscience and Biobehavioral Reviews"},{"issue":"1","key":"2021121723253931000_B56","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1016\/j.neuroimage.2011.12.027","article-title":"Performance evaluation of the Champagne source reconstruction algorithm on simulated and real M\/EEG data","volume":"60","author":"Owen","year":"2012","journal-title":"NeuroImage"},{"key":"2021121723253931000_B57","doi-asserted-by":"crossref","DOI":"10.1201\/b11527","author":"Ozaki","year":"2012","journal-title":"Time series modeling of neuroscience data"},{"key":"2021121723253931000_B58","doi-asserted-by":"crossref","first-page":"1324","DOI":"10.1109\/CDC.2010.5717549","article-title":"An adaptive-covariance-rank algorithm for the unscented Kalman filter.","author":"Padilla","year":"2010","journal-title":"Proceedings of the 49th IEEE Conference on Decision and Control"},{"key":"2021121723253931000_B59","doi-asserted-by":"crossref","DOI":"10.3389\/fnins.2017.00635","article-title":"Spatiotemporal EEG source imaging with the hierarchical Bayesian elastic net and elitist lasso models","volume":"11","author":"Paz-Linares","year":"2017","journal-title":"Frontiers in Neuroscience"},{"key":"2021121723253931000_B60","author":"Penny","year":"2007","journal-title":"Statistical parametric mapping"},{"issue":"3","key":"2021121723253931000_B61","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1007\/s10115-017-1053-1","article-title":"Crowd labeling latent Dirichlet allocation","volume":"53","author":"Pion-Tonachini","year":"2017","journal-title":"Knowledge and Information Systems"},{"key":"2021121723253931000_B62","doi-asserted-by":"crossref","DOI":"10.1088\/1741-2552\/aa69d1","article-title":"Automated EEG artifact elimination by applying machine learning algorithms to ICA-based features.","volume":"14","author":"Rad\u00fcntz","year":"2017","journal-title":"Journal of Neural Engineering"},{"key":"2021121723253931000_B63","doi-asserted-by":"crossref","DOI":"10.7717\/peerj.4380","article-title":"A new ICA- based fingerprint method for the automatic removal of physiological artifacts from EEG recordings","volume":"6","author":"Tamburro","year":"2018","journal-title":"PeerJ"},{"key":"2021121723253931000_B64","first-page":"211","article-title":"Sparse Bayesian Learning and the Relevance Vector Machine","volume":"1","author":"Tipping","year":"2001","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"2021121723253931000_B65","doi-asserted-by":"crossref","DOI":"10.1186\/1743-0003-8-24","article-title":"Brain-computer interfacing using modulations of alpha activity induced by covert shifts of attention","volume":"8","author":"Treder","year":"2011","journal-title":"Journal of NeuroEngineering and Rehabilitation"},{"key":"2021121723253931000_B66","doi-asserted-by":"crossref","first-page":"2701","DOI":"10.1002\/hbm.20704","article-title":"Model driven EEG\/fMRI fusion of brain oscillations","volume":"30","author":"Valdes-Sosa","year":"2009","journal-title":"Human Brain Mapping"},{"issue":"6","key":"2021121723253931000_B67","doi-asserted-by":"crossref","first-page":"1898","DOI":"10.1002\/hbm.20784","article-title":"EEG source imaging with spatio-temporal tomographic nonnegative independent component analysis.","volume":"30","author":"Vald\u00e9s-Sosa","year":"2009","journal-title":"Human Brain Mapping"},{"key":"2021121723253931000_B68","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van Der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"2021121723253931000_B69","first-page":"1256","article-title":"Feedback-related negativity.","author":"Ward","year":"2013","journal-title":"Encyclopedia of autism spectrum disorders"},{"issue":"1","key":"2021121723253931000_B70","doi-asserted-by":"crossref","DOI":"10.1186\/1744-9081-7-30","article-title":"Automatic classification of artifactual ICA: Components for artifact removal in EEG signals","volume":"7","author":"Winkler","year":"2011","journal-title":"Behavioral and Brain Functions"},{"key":"2021121723253931000_B71","first-page":"1625","volume-title":"Advances in neural information processing systems","author":"Wipf","year":"2008"},{"issue":"1","key":"2021121723253931000_B72","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1016\/j.neuroimage.2009.06.083","article-title":"Robust Bayesian estimation of the location, orientation, and time course of multiple correlated neural sources using MEG","volume":"49","author":"Wipf","year":"2010","journal-title":"NeuroImage"},{"issue":"4","key":"2021121723253931000_B73","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1002\/hbm.20000","article-title":"Recursive penalized least squares solution for dynamical inverse problems of EEG generation","volume":"235","author":"Yamashita","year":"2004","journal-title":"Human Brain Mapping"},{"key":"2021121723253931000_B74","volume-title":"Advances in neural information processing systems","author":"Yang","year":"2016"},{"issue":"8","key":"2021121723253931000_B75","doi-asserted-by":"crossref","first-page":"2009","DOI":"10.1109\/TSP.2013.2241055","article-title":"Extension of SBL algorithms for the recovery of block sparse signals with intra-block correlation","volume":"61","author":"Zhang","year":"2013","journal-title":"IEEE Transactions on Signal Processing"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/33\/9\/2408\/1978141\/neco_a_01415.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/33\/9\/2408\/1978141\/neco_a_01415.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,2]],"date-time":"2023-01-02T05:41:39Z","timestamp":1672638099000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/33\/9\/2408\/102623\/Bridging-M-EEG-Source-Imaging-and-Independent"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,19]]},"references-count":75,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2021,8,19]]},"published-print":{"date-parts":[[2021,8,19]]}},"URL":"https:\/\/doi.org\/10.1162\/neco_a_01415","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,9]]},"published":{"date-parts":[[2021,8,19]]}}}